Video caption questions
Can my iPhone turn the speech in a video into text?
Yes, with an app. Captionry transcribes the speech in a video on your iPhone, with every word timed, and exports the text as an SRT or WebVTT subtitle file that opens in any text editor and in many video editors. You can also keep the text on the video as burned-in captions. Making captions and exporting the file are free and do not use AI minutes.
What to know
- SRT and WebVTT are plain-text subtitle files: each caption has a start time, an end time and its text.
- WebVTT is a W3C standard for captions on the web; SRT is the older format that most players and editors read.
- Captionry exports SRT, WebVTT or a Captionry JSON project file. Files are made on your iPhone and are not uploaded.
- Accuracy depends on clear speech; loud music or people talking over each other lowers it.
Checked: October 2026 · Sources: w3.org
How to do it with Captionry
- Open Captionry, pick your video and choose the language spoken.
- Let Captionry write the captions, then tap any word to fix it.
- Tap Languages, then Subtitle file under More options.
- Export SRT or WebVTT and save it to Files or share it to another app.
Related questions
Can I get the words without the times?
Captionry exports subtitle files, which include times. Open the SRT file in any text editor to copy the words.
Does it work on long videos?
Yes. There is no length limit for captions made on your iPhone; on an iPhone 14, a 10-minute clip takes under 8 minutes. Optional AI polish takes videos up to 30 minutes and 400 captions.
Which languages can it transcribe?
The languages your iPhone can recognise on the device, such as English, Chinese, Japanese, Spanish and German.
Caption your video in Captionry
Captions are made on your iPhone. Making captions, editing and exporting without a watermark are free; optional AI polish includes 15 free video minutes a month. iPhone only.
Download on the App Store